60 stories tagged with #agents, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Agents"
Welcome to Agents Week
Agents Week explores how cloud infrastructure must evolve to serve autonomous agents rather than human browsers. Join us as we unpack the storage, execution, and security primitive…
Experts say US law is unprepared for rogue AI agents and models, as recent OpenAI and Anthropic incidents raise questions over legal liability and repercussions (Lily Hay Newman/Wired)
How to Apply Coding Agents to Non-Programming Tasks
Perform non-programming tasks with coding agents…
Show HN: MCP server so AI agents can screen markets in plain English
Contribute to xcreener/xcreener-mcp development by creating an account on GitHub.…
Do Not Trust, Continuously Verify (Your AI Agents)
Show HN: Rails Agent – Build Autonomous AI Agents Natively in Ruby on Rails
The fullstack agentic platform for Ruby on Rails. One gem install, docs-first build path, Playbooks, BYOK provider keys, test, deploy, and monitor.…
OpenAI is investigating more incidents of AI agents going rogue days after hack - Digital Trends
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
OpenAI is investigating more incidents of AI agents going rogue days after hack
It appears that the “AI agents going rogue” tale has more to it than what AI giants have revealed publicly so far. Merely days after OpenAI announced that its AI agents went rogue …
OpenAI Presence wants to make AI agents production-ready for businesses - the-decoder.com
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Show HN: Handoff is await human() for AI agents
await human() for AI agents: when an agent hits a wall, a real phone rings and a person takes the wheel in its live browser. - OmegaAgent/handoff…
OpenAI uncovers more rogue AI agents during Hugging Face investigation - Cybernews
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Agent-Browser – Browser Automation for AI
Browser automation CLI for AI agents…
Ask HN: I still don't understand why AI agents need "skills"
AI Agents At OpenAI, Anthropic, Microsoft Broke Out, Broke In, Obeyed - Forbes
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Coding Agents Don’t Need Bigger Context Windows — They Need a Context Compiler
Most coding agents treat prompt construction like retrieval: gather more files, add more context, hope the model figures it out. But that approach breaks down fast. As context grow…
OpenAI’s powerful AI agents ran amok and hacked multiple services on their own - Yahoo Tech
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
OpenAI Breach Probe Widens: More Agents Escaped Containment, Notes Found Coaching Future Versions - Tech Times
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Tel Aviv-based Bloom Security, which develops endpoint security tools for monitoring AI agents, extensions, and more, emerges from stealth with a $20M seed (Chris Metinko/Axios)
Ace Sidecar – Efficiency Optimization for Local AI Coding
A local proxy that sits in front of your coding agent and tells you what each session actually cost, where the time went, and which optimisations would be worth anything on your tr…
OpenAI finds evidence other AI agents escaped containment as it widens hacking probe - The Japan Times
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
OpenAI finds more AI agents escaped containment in hacking probe - news.cgtn.com
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
OpenAI reportedly detects more rogue AI agents escaping controls as hacking probe intensifies - TRT World
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Show HN: GAI – A Go runtime for typed, tool-using LLM agents
🤖 Type-safe, provider-neutral agent runtime for Go with native tools, memory, and OpenTelemetry - lace-ai/gai…
OpenAI reportedly finds evidence that more of its agents ran amok - TechCrunch
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
OpenAI reportedly finds evidence that more of its agents ran amok
OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.…
OpenAI finds evidence other AI agents escaped containment as probe widens - Honolulu Star-Advertiser
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Exclusive-OpenAI finds evidence other AI agents escaped containment as it widens hacking probe - KELO-AM
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Exclusive-OpenAI finds evidence other AI agents escaped containment as it widens hacking probe - whbl.com
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Sources: OpenAI has discovered other instances where AI agents escaped containment; none of the agents were thought to have left OpenAI's network (Reuters)
OpenAI finds evidence other AI agents escaped containment as it widens probe
EXCLUSIVE: OpenAI finds evidence other AI agents escaped containment as it widens hacking probe - Reuters
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
MCP is going stateless: What the new spec means for AI agents
The Model Context Protocol (MCP) is going stateless. Discover how this architecture shift simplifies agent scaling and integrates OpenTelemetry.…
Orca-Bench: How Ready Are Language Model Agents for Oncall?
Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source co…
Anthropic and OpenAI are competing to see whose agents can go rogue harder
Whoever wins, we lose…
13 Models and 4 Agents on SWE Tasks: Go, Java, Python, Rust, TS
SWE-rebench: A Continuously Evolving and Decontaminated Benchmark for Software Engineering LLMs.…
Anthropic and OpenAI are competing to see whose agents can go rogue harder - The Register
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Claude Code's sub-agents solve one problem and create three others
Isolation giveth, and isolation taketh away.…
Pennant Knowledge Engineering Studio – Compile Graph Context for AI Agents
Knowledge Engineering Studio. Contribute to galeluka/Pennant development by creating an account on GitHub.…
How to Debug AI Coding Agents When They Change the Wrong Thing
A practical tutorial for recording model tool requests, real function results, patches, checks, screenshots, and a saved run log.…
Building Voice-Controlled AI Agents
Building a voice-controlled AI agents isn't hard, this article breaks the pipeline into its real components: streaming speech recognition, turn detection, streaming generation, int…
Stealthy Concurrent Audio Prompt Injections Against Multimodal LLM Agents
Large Language Model (LLM)-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction…
EU in talks with OpenAI and Anthropic following attacks on AI agents - Techzine Global
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Show HN: Secure Bearer JWT and JWKS pattern for headless AI agents (MCP #824)
Pre-submission Checklist This post follows the MCP community guidelines What would you like to share? Security: Bearer JWT + JWKS for agent callers (no master secret in the LLM pat…
Show HN: Emem Channel - Signed collaboration between independent AI agents
A week of agents building a memory protocol and trying to break each other's claims. 7 of 10 corrections were made by the party they damaged. Every message signed, addressable, and…
Why Enterprise AI Gets Hard After the First Agent
Most enterprise AI initiatives begin with a chatbot.…
Show HN: I stopped babysitting my AI agents by pushing them to Telegram
BlackFlare — a menu bar app for Claude Code and Codex. Keep your Mac awake during long runs, get notified when tasks finish, switch defaults, track usage.…
AdaMAST: Adaptive Failure Taxonomies for Improving LLM Agents
Convert an agent system's traces into a compact taxonomy of named failure codes on three fixed axes, induced automatically and validated before anything trusts them.…
Show HN: What should the GUI for AI agents look like?
A workspace with visible files, tools, tasks, and outputs — not buried in chat threads.…
ResiliReplay – Chaos testing for AI agents and MCP servers
Crash-test AI agents and MCP servers, replay failures, and turn broken traces into deterministic regression tests. - aliengineering-byte/resilireplay…
OpenAI Trains Faculty and Researchers to Use Coding Agents - GovTech
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Empathy: A skill that helps AI agents talk to humans
A skill that helps AI agents talk to humans. Contribute to danielroe/empathy development by creating an account on GitHub.…
OpenAI’s ‘rogue’ agents hacked into more systems than initially reported - NBC News
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Hush Security says the AI security problem has shifted from protecting models to governing identities as autonomous agents spread
Echoverse: Deep, evolving environments for computer-use agents
Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more train…
Can AI agents conduct open-ended AI research?
Forecasts of explosive AI progress hinge on AI agents automating AI research. But evidence on whether agents can carry out open-ended AI research is thin. Current evaluations eithe…
Show HN: Noisegate – a differential-privacy gateway for untrusted AI agents
Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's recor…
Git worktrees are not an isolation boundary for coding agents
Most tools that run AI coding agents in parallel give each one a git worktree. A worktree shares refs, config, stash and hooks with your real repository. Paste-and-run repros showi…
Designing Docs for AI Agents
Anthropic crawls ~38,000 pages per visitor it refers back. How to design docs for AI agents: markdown endpoints, llms.txt, MCP, and errors as content.…
Show HN: Wasted Cycles – Local wall-clock profiler for AI coding agents
Wasted Cycles is a local terminal profiler that reads the Codex, Claude Code, Cursor, and Grok Build traces already on your machine and shows where a run stopped coding: model work…
New details in the OpenAI Hugging Face hack show how far agents will go: 'It's now remarkably easy' - CNBC
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…